© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94666
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -1.24
    tvguidetime
    -0.70
    ientí
    -0.56
    CROSSTALK
    -0.49
     متعلقه
    -0.49
    Soda
    -0.49
    homonymie
    -0.48
    (/[
    -0.48
     kopp
    -0.47
    tagHelperRunner
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.71
    quelize
    0.70
    出版年
    0.68
     same
    0.61
    DockStyle
    0.56
    luss
    0.56
    ToMany
    0.55
    jspx
    0.54
     sare
    0.54
     existence
    0.54
    Activations Density 0.105%

    No Known Activations